Downloads · 30 days
0
sdxl_neuron_pipe
paulkm/sdxl_neuron_pipe
sdxl_neuron_pipe is a text-to-image model from paulkm. Use it when you need an image from a text prompt. It is set up for optimum_neuronx.
This is a model compiled for optimized inference on AWS inf2 instances. The overall performance can achieve 4it/s for a 1024x1024 picture.
Access
Public
Updated Sep 19, 2023
Repo size
7.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.neuron7.5 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- optimum_neuronx
- Access
- Public
- Created
- Sep 19, 2023
- Updated
- Sep 19, 2023
- SHA
- 2dbf63e1
Model card
From the Hugging Face model README
This is a model compiled for optimized inference on AWS inf2 instances. The overall performance can achieve 4it/s for a 1024x1024 picture.
NOTE: In order to load and infer on inf2.xlarge instances, a minimum of 8 GB SWAP memory is required. Other instance sizes do not require this.
Assuming you're using the official DLAMI or installed the drivers and libraries required for neuron devices, install the latest optimum_neuronx library:
pip install -U optimum[neuronx] diffusers=0.20.0
Then, enjoy the super-fast experience:
from optimum.neuron import NeuronStableDiffusionXLPipeline
pipe = NeuronStableDiffusionXLPipeline.from_pretrained("paulkm/sdxl_neuron_pipe", device_ids=[0,1])
img = pipe("a cute black cat").images[0]
- Task
- Text-to-Image
- Library
- optimum_neuronx
- Created
- Sep 19, 2023
- Updated
- Sep 19, 2023